data <- read.csv("owid-covid-data.csv")
data <- data %>% mutate(cases = total_cases,
deaths = total_deaths,
vac1 = people_vaccinated,
vac2 = people_fully_vaccinated,
pop = population)
data <- data %>% select(continent,
location,
cases,
deaths,
vac1,
vac2,
date,
pop)
data <- data %>% filter(!(location %in% c("World",
"Asia",
"Europe",
"North America",
"European Union",
"South America",
"Africa",
"Oceania",
"International",
"Northern Cyprus"))) #NA's
glimpse(data)## Rows: 112,772
## Columns: 8
## $ continent <fct> Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, ~
## $ location <fct> Afghanistan, Afghanistan, Afghanistan, Afghanistan, Afghanis~
## $ cases <dbl> 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 8, 8, 8, 8, 11, 11, 11, ~
## $ deaths <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ~
## $ vac1 <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ~
## $ vac2 <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ~
## $ date <fct> 2020-02-24, 2020-02-25, 2020-02-26, 2020-02-27, 2020-02-28, ~
## $ pop <dbl> 39835428, 39835428, 39835428, 39835428, 39835428, 39835428, ~summary(data)## continent location cases deaths
## : 0 Argentina : 630 Min. : 1 Min. : 1
## Africa :30055 Mexico : 630 1st Qu.: 1796 1st Qu.: 63
## Asia :27371 Peru : 630 Median : 16850 Median : 482
## Europe :27795 Thailand : 627 Mean : 457126 Mean : 11681
## North America:15185 Taiwan : 615 3rd Qu.: 165550 3rd Qu.: 4085
## Oceania : 5398 South Korea: 610 Max. :42410607 Max. :678407
## South America: 6968 (Other) :109030 NA's :5685 NA's :16223
## vac1 vac2 date
## Min. :0.000e+00 Min. :1.000e+00 2021-06-21: 219
## 1st Qu.:1.559e+05 1st Qu.:7.920e+04 2021-06-22: 219
## Median :9.441e+05 Median :6.225e+05 2021-06-23: 219
## Mean :8.855e+06 Mean :5.664e+06 2021-06-24: 219
## 3rd Qu.:4.753e+06 3rd Qu.:3.372e+06 2021-06-25: 219
## Max. :1.101e+09 Max. :1.022e+09 2021-06-26: 219
## NA's :89772 NA's :92634 (Other) :111458
## pop
## Min. :4.700e+01
## 1st Qu.:1.933e+06
## Median :8.715e+06
## Mean :4.099e+07
## 3rd Qu.:2.967e+07
## Max. :1.444e+09
## data <- data %>%
mutate(date_aux = as.Date(date)) %>%
filter(date_aux>"2020-01-01") %>%
group_by(location, month(date_aux)) %>%
filter(date_aux == max(date_aux))
data <- data %>%
group_by(location) %>%
fill(cases,
deaths,
vac1,
vac2, .direction = c("down"))
data <- data %>%
group_by(location) %>%
mutate(cases = 100*replace_na(cases,0)/pop,
deaths = 100*replace_na(deaths,0)/pop,
vac1 = 100*replace_na(vac1,0)/pop,
vac2 = 100*replace_na(vac2,0)/pop)
data<- data %>% mutate(date_num = as.numeric(date_aux)-18565 )
data <- data %>% select(-pop)summary(data)## continent location cases
## : 0 Afghanistan : 12 Min. : 0.00000
## Africa :652 Albania : 12 1st Qu.: 0.09272
## Asia :573 Algeria : 12 Median : 0.87755
## Europe :595 Andorra : 12 Mean : 2.55694
## North America:359 Angola : 12 3rd Qu.: 3.91616
## Oceania :164 Antigua and Barbuda: 12 Max. :21.30927
## South America:147 (Other) :2418
## deaths vac1 vac2 date
## Min. :0.000000 Min. : 0.00 Min. : 0.000 2021-06-30: 219
## 1st Qu.:0.001048 1st Qu.: 0.00 1st Qu.: 0.000 2021-07-31: 219
## Median :0.011024 Median : 0.00 Median : 0.000 2021-08-31: 218
## Mean :0.045915 Mean : 11.96 Mean : 8.150 2021-05-31: 216
## 3rd Qu.:0.068716 3rd Qu.: 13.22 3rd Qu.: 4.853 2021-04-30: 213
## Max. :0.596713 Max. :118.35 Max. :117.132 2021-03-31: 210
## (Other) :1195
## date_aux month(date_aux) date_num
## Min. :2020-10-31 Min. : 1.000 Min. : 1.0
## 1st Qu.:2021-01-31 1st Qu.: 4.000 1st Qu.: 93.0
## Median :2021-04-30 Median : 6.000 Median :182.0
## Mean :2021-04-20 Mean : 6.425 Mean :172.4
## 3rd Qu.:2021-07-31 3rd Qu.: 9.000 3rd Qu.:274.0
## Max. :2021-09-21 Max. :12.000 Max. :326.0
## glimpse(data)## Rows: 2,490
## Columns: 10
## Groups: location [223]
## $ continent <fct> Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia~
## $ location <fct> Afghanistan, Afghanistan, Afghanistan, Afghanistan, ~
## $ cases <dbl> 0.1037619, 0.1160148, 0.1313655, 0.1381258, 0.139860~
## $ deaths <dbl> 0.003848333, 0.004425709, 0.005495109, 0.006024788, ~
## $ vac1 <dbl> 0.00000000, 0.00000000, 0.00000000, 0.00000000, 0.02~
## $ vac2 <dbl> 0.0000000, 0.0000000, 0.0000000, 0.0000000, 0.000000~
## $ date <fct> 2020-10-31, 2020-11-30, 2020-12-31, 2021-01-31, 2021~
## $ date_aux <date> 2020-10-31, 2020-11-30, 2020-12-31, 2021-01-31, 202~
## $ `month(date_aux)` <dbl> 10, 11, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 1~
## $ date_num <dbl> 1, 31, 62, 93, 121, 152, 182, 213, 243, 274, 305, 32~#data %>% filter_all(any_vars(is.na(.)))names <- c('Brazil',
'United States',
'Canada',
'Mexico',
'Germany',
'United Kingdom',
'French',
'Italy',
'Spain',
'Russia',
'India',
'South Korea',
'China',
'Japan',
'Australia')
colors <- c('#F28B30', # Asia (laranja)
'#BF0A3A', # Europa (vermelho)
'#022873', # Am?rica do norte (azul)
'#F23D6D', # Oceania (rosa)
'gray', # Outros (cinza)
'#03A62C') # Am?rica do sul (verde)describe(data)p <- data %>%
ggplot(aes(x=cases,
y=deaths,
size=vac2)) +
geom_point(aes(color=continent,
frame=date_num,
ids=location),alpha=0.6) +
scale_size(range = c(.1, 24), name="fully vaccinated") +
scale_colour_manual(values = colors) +
xlim(-1, 20) +
ylim(-0.07, .61) +
theme_classic() +
theme(legend.position = c(0.83, 0.86)) +
guides(size = 'none') +
labs(title="COVID-19 vaccinations of top 15 GPD countries")## Warning: Ignoring unknown aesthetics: frame, ids[ref animation plotly][https://plotly-r.com/animating-views.html]
ggplotly(p)p## Warning: Removed 3 rows containing missing values (geom_point).